{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JVZNAQDY2UV2OJB4D5COL7OGXJ","short_pith_number":"pith:JVZNAQDY","schema_version":"1.0","canonical_sha256":"4d72d04078d52ba7243c1f44e5fdc6ba693de3ddfb48e4c9af402a840a64aa65","source":{"kind":"arxiv","id":"2211.15457","version":2},"attestation_state":"computed","paper":{"title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charlotte Morissette, David Meger, Francois Robert Hogan, Gregory Dudek, Sahand Rezaei-Shoshtari","submitted_at":"2022-11-28T15:48:35Z","abstract_excerpt":"In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hyperne"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.15457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T15:48:35Z","cross_cats_sorted":[],"title_canon_sha256":"9040f941b0fa6996f186492b6baf1a23112d9edccad187ea170c58aa293c6e3a","abstract_canon_sha256":"f49530c2fae81687ecb4b69a865dc3d5b3896fba443eb2fea4847e3bb884d2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:55.230823Z","signature_b64":"/AAGUECQubfcUTZbJjCj9SLcndIwN5CuiVX1kg7a5FKGIzao8Ff8u071DtMfHmeLgl6gz6DSsBwJyMv0ipvDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d72d04078d52ba7243c1f44e5fdc6ba693de3ddfb48e4c9af402a840a64aa65","last_reissued_at":"2026-07-05T05:29:55.230337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:55.230337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charlotte Morissette, David Meger, Francois Robert Hogan, Gregory Dudek, Sahand Rezaei-Shoshtari","submitted_at":"2022-11-28T15:48:35Z","abstract_excerpt":"In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hyperne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15457","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.15457/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.15457","created_at":"2026-07-05T05:29:55.230397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15457v2","created_at":"2026-07-05T05:29:55.230397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15457","created_at":"2026-07-05T05:29:55.230397+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVZNAQDY2UV2","created_at":"2026-07-05T05:29:55.230397+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVZNAQDY2UV2OJB4","created_at":"2026-07-05T05:29:55.230397+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVZNAQDY","created_at":"2026-07-05T05:29:55.230397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12388","citing_title":"Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12388","citing_title":"Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ","json":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ.json","graph_json":"https://pith.science/api/pith-number/JVZNAQDY2UV2OJB4D5COL7OGXJ/graph.json","events_json":"https://pith.science/api/pith-number/JVZNAQDY2UV2OJB4D5COL7OGXJ/events.json","paper":"https://pith.science/paper/JVZNAQDY"},"agent_actions":{"view_html":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ","download_json":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ.json","view_paper":"https://pith.science/paper/JVZNAQDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15457&json=true","fetch_graph":"https://pith.science/api/pith-number/JVZNAQDY2UV2OJB4D5COL7OGXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JVZNAQDY2UV2OJB4D5COL7OGXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ/action/storage_attestation","attest_author":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ/action/author_attestation","sign_citation":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ/action/citation_signature","submit_replication":"https://pith.science/pith/JVZNAQDY2UV2OJB4D5COL7OGXJ/action/replication_record"}},"created_at":"2026-07-05T05:29:55.230397+00:00","updated_at":"2026-07-05T05:29:55.230397+00:00"}